Long-range forecasting of IBM product revenues using a seasonal fractionally differenced ARMA model

Long-range forecasting of IBM product revenues using a seasonal fractionally differenced ARMA model

0.00 Avg rating0 Votes
Article ID: iaor1994439
Country: Netherlands
Volume: 9
Issue: 2
Start Page Number: 255
End Page Number: 269
Publication Date: Apr 1993
Journal: International Journal of Forecasting
Authors:
Keywords: financial
Abstract:

The paper uses a series of monthly IBM product revenues to illustrate the usefulness of seasonal fractionally differenced ARMA models for business forecasting. By allowing two seasonal fractional differencing parameters in the model, one at lag three and the other at lag twelve, it obtains a stationary series without losing information about the process behavior through over-differencing. The paper applies modified identification and estimation techniques to the IBM revenue data and compares the resulting model with a specific non-fractional seasonal ARIMA model by looking at each model’s forecasts. The fractionally differenced seasonal model gives more accurate next-quarter, next-half-year, next-year, and next-two-years forecasts than the non-fractional seasonal model based on criteria that are specifically constructed to reflect the accuracy of long-range periodic forecasts.

Reviews

Required fields are marked *. Your email address will not be published.